Disentangling Multiple Conditional Inputs in GANs
arXiv:1806.07819
Abstract
In this paper, we propose a method that disentangles the effects of multiple input conditions in Generative Adversarial Networks (GANs). In particular, we demonstrate our method in controlling color, texture, and shape of a generated garment image for computer-aided fashion design. To disentangle the effect of input attributes, we customize conditional GANs with consistency loss functions. In our experiments, we tune one input at a time and show that we can guide our network to generate novel and realistic images of clothing articles. In addition, we present a fashion design process that estimates the input attributes of an existing garment and modifies them using our generator.
arXiv comment5 pages, 9 figures, Paper is accepted to the workshop "AI for Fashion" in KDD Conference, 2018, London, United Kingdom
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Conditional Generative Adversarial Nets
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Improved Training of Wasserstein GANs
- Generative Visual Manipulation on the Natural Image Manifold
- Deep Photo Style Transfer
- DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
- Be Your Own Prada: Fashion Synthesis with Structural Coherence
- Fashion DNA: Merging Content and Sales Data for Recommendation and Article Mapping